This study aimed to investigate the correlation between COVID-19 and the direct antiglobulin test (DAT) and establish an in-hospital mortality risk predictive model based on the DAT type, which can be used for the early prediction of inpatients with COVID-19.
In this study, 502 patients admitted to our hospital who underwent DAT testing from January 29 to February 8, 2023, were included (252 DAT-positive and 250 DAT-negative). Among them, 241 cases of COVID-19 were screened(171 DAT-positive and 70 DAT-negative), clinical and laboratory indicators were compared between DAT-positive and DAT-negative groups. Univariate and multivariate logistic regression analysis, the Kaplan-Meier survival curve and receiver operating curves were used to explore the relation between the DAT type and in-hospital mortality of patients with COVID-19.
The proportion of confirmed COVID-19 cases was higher in the DAT-positive group than in the DAT-negative group (67.9 % vs. 28.0 %, P < 0.05). Patients with COVID-19 in the DAT-positive group had higher age-adjusted Charlson comorbidity index scores, red blood cell distribution width (RDW), lactate dehydrogenase, prothrombin time, D-dimer, creatinine, and high-sensitive cardiac troponin T levels than the negative group (P < 0.05), In contrast, hemoglobin and estimated glomerular filtration rate (eGFR) levels were lower in the DAT-positive group. The DAT-positive group also had a higher red blood cell usage volume and in-hospital mortality rate than the DAT-negative group. The mortality rate of patients with COVID-19 with both IgG and C3d positive was higher than that of the other groups. Multivariate logistic regression analysis showed that RDW and eGFR were associated with mortality in patients with COVID-19. The combined predictive model of DAT type, RDW, and eGFR showed an area under the curve of 0.782, sensitivity of 0.769, and specificity of 0.712 in predicting in-hospital mortality risk in patients with COVID-19.
The established predictive model for in-hospital mortality risk of patients with COVID-19 based on DAT type, RDW, and eGFR can provide a basis for timely intervention to reduce the mortality rates of patients with COVID-19. This model is accessible at https://jijijiduola.shinyapps.io/0531// for research purposes.
Artificial Intelligence is transforming drug discovery, particularly in the hit identification phase of therapeutic compounds. One tool that has been instrumental in this transformation is Quantitative Structure-Activity Relationship (QSAR) analysis. This computer-aided drug design tool uses machine learning to predict the biological activity of new compounds based on the numerical representation of chemical structures against various biological targets. With diabetes mellitus becoming a significant health challenge in recent times, there is intense research interest in modulating antidiabetic drug targets. α-Glucosidase is an antidiabetic target that has gained attention due to its ability to suppress postprandial hyperglycaemia, a key contributor to diabetic complications. This review explored a detailed approach to developing QSAR models, focusing on strategies for generating input variables (molecular descriptors) and computational approaches ranging from classical machine learning algorithms to modern deep learning algorithms. We also highlighted studies that have used these approaches to develop predictive models for α-glucosidase inhibitors to modulate this critical antidiabetic drug target.
To assess technical usability of the BigO app and clinical portal among diverse participants and explore the overall user experiences of both.
Methods included technical usability testing by measuring the relative user efficiency score (RUS) for the app and measuring Relative User Efficiency (RUE) using the ‘think aloud’ method with the clinical portal. Qualitative approaches involved focus groups with adolescent app users and semi-structured one-to-one interviews with clinician participants. Thematic analysis was applied to analyze qualitative data.
Clinical participants consisted of adolescents seeking treatment for severe obesity and were invited via telephone/face to face to attend technical usability testing and a focus group. Healthcare professionals (HCPs) and researchers using the BigO clinical portal interface were invited to participate in usability testing and semi-structured interviews.
From 14 families invited to attend, seven consented to join the study and four adolescents (mean age=13.8 (SD 0.8) years) participated. Additionally, six HCPs and one pediatric obesity researcher took part. RUS for adolescents indicated that the tasks required of them via myBigO app were feasible, and technically efficient. No user-related errors were observed during tasks. Technical barriers reported by adolescents included notifications of battery optimization, misunderstanding image annotation language, and compatibility challenges with certain phone models. RUS for the HCPs and researcher indicated that basic technical skills are a potential barrier for clinical portal use and qualitative findings revealed that clinical users wanted a logging option for monitoring goals and providing feedback on the portal.
Our study provided valuable formative findings from clinical end-users in Ireland indicating that adolescents being treated for obesity rated myBigO app as usable, acceptable and that it may assist other key stakeholders to understand food marketing and to monitor dietary and physical activity behaviors. Several key suggestions for future iterations of the clinical portal were provided to enhance its value in pediatric obesity treatment.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：